scPriorGraph: constructing biosemantic cell–cell graphs with prior gene set selection for cell type identification from scRNA-seq data
Cell type identification is an indispensable analytical step in single-cell data analyses. To address the high noise stemming from gene expression data, existing computational methods often overlook the biologically meaningful relationships between genes, opting to reduce all genes to a unified data space. We assume that such relationships can aid in characterizing cell type features and improving cell type recognition accuracy. To this end, we introduce scPriorGraph, a dual-channel graph neural network that integrates multi-level gene biosemantics. Experimental results demonstrate that scPriorGraph effectively aggregates feature values of similar cells using high-quality graphs, achieving state-of-the-art performance in cell type identification.
Authors
- Xiyue Cao (ORCID: https://orcid.org/0000-0001-8789-8762)
- Lun Hu (ORCID: https://orcid.org/0000-0002-1591-8549)
- Xuequn Shang (ORCID: https://orcid.org/0000-0002-7249-8210)
- Yu‐An Huang (ORCID: https://orcid.org/0000-0002-5346-2394)
- Zhu‐Hong You (ORCID: https://orcid.org/0000-0003-1266-2696)
- Pengwei Hu (ORCID: https://orcid.org/0000-0001-5974-7932)
- Zhi-An Huang (ORCID: https://orcid.org/0000-0001-9974-148X)
Institutions
- City University of Hong Kong (HK)
- Northwestern Polytechnical University (CN)
- Chinese Academy of Sciences (CN)
- Xinjiang Technical Institute of Physics & Chemistry (CN)
- City College of Dongguan University of Technology (CN)
- Northwestern Polytechnic University (US)
Publication Details
- Journal
- Genome biology
- Published
- 2024-08-05
- DOI
- https://doi.org/10.1186/s13059-024-03357-w
- Citations
- 24
- Primary Topic
- Single-cell and spatial transcriptomics
- Type
- article
- Field-Weighted Citation Impact
- 5.61
Funders
- Natural Science Foundation of Guangdong Province
- Central University Basic Research Fund of China
- Fundamental Research Funds for the Central Universities
- National Science Fund for Distinguished Young Scholars
- Specific Research Project of Guangxi for Research Bases and Talents